© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 158465
    Prev
    Next
    INDEX
    Explanations

    together with

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    quear
    0.41
    랠
    0.39
    ज़र
    0.38
    pector
    0.38
    QUIN
    0.38
     Filler
    0.36
     Defin
    0.36
     Yelp
    0.36
    unin
    0.36
     вакан
    0.36
    POSITIVE LOGITS
    \[
    0.39
    のひとつ
    0.38
    热
    0.38
    Tom
    0.38
    लं
    0.38
    DD
    0.36
    HG
    0.36
    JD
    0.36
    RA
    0.36
    Heat
    0.36
    Activations Density 0.001%

    No Known Activations